read-cache.c 61.7 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5
/*
 * GIT - The information manager from hell
 *
 * Copyright (C) Linus Torvalds, 2005
 */
6
#define NO_THE_INDEX_COMPATIBILITY_MACROS
7
#include "cache.h"
8
#include "tempfile.h"
9
#include "lockfile.h"
10
#include "cache-tree.h"
11
#include "refs.h"
12
#include "dir.h"
13 14
#include "tree.h"
#include "commit.h"
15
#include "blob.h"
16
#include "resolve-undo.h"
17 18
#include "strbuf.h"
#include "varint.h"
Duy Nguyen's avatar
Duy Nguyen committed
19
#include "split-index.h"
20
#include "utf8.h"
21

22 23
static struct cache_entry *refresh_cache_entry(struct cache_entry *ce,
					       unsigned int options);
24

25 26 27 28
/* Mask for the name length in ce_flags in the on-disk index */

#define CE_NAMEMASK  (0x0fff)

29 30 31 32 33 34 35 36 37 38 39
/* Index extensions.
 *
 * The first letter should be 'A'..'Z' for extensions that are not
 * necessary for a correct operation (i.e. optimization data).
 * When new extensions are added that _needs_ to be understood in
 * order to correctly interpret the index file, pick character that
 * is outside the range, to cause the reader to abort.
 */

#define CACHE_EXT(s) ( (s[0]<<24)|(s[1]<<16)|(s[2]<<8)|(s[3]) )
#define CACHE_EXT_TREE 0x54524545	/* "TREE" */
40
#define CACHE_EXT_RESOLVE_UNDO 0x52455543 /* "REUC" */
Duy Nguyen's avatar
Duy Nguyen committed
41
#define CACHE_EXT_LINK 0x6c696e6b	  /* "link" */
42
#define CACHE_EXT_UNTRACKED 0x554E5452	  /* "UNTR" */
Duy Nguyen's avatar
Duy Nguyen committed
43 44

/* changes that can be kept in $GIT_DIR/index (basically all extensions) */
45
#define EXTMASK (RESOLVE_UNDO_CHANGED | CACHE_TREE_CHANGED | \
46
		 CE_ENTRY_ADDED | CE_ENTRY_REMOVED | CE_ENTRY_CHANGED | \
47
		 SPLIT_INDEX_ORDERED | UNTRACKED_CHANGED)
48

49
struct index_state the_index;
50
static const char *alternate_index_output;
51

Junio C Hamano's avatar
Junio C Hamano committed
52 53 54
static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
	istate->cache[nr] = ce;
55
	add_name_hash(istate, ce);
Junio C Hamano's avatar
Junio C Hamano committed
56 57
}

58 59 60 61
static void replace_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
	struct cache_entry *old = istate->cache[nr];

62
	replace_index_entry_in_base(istate, old, ce);
63
	remove_name_hash(istate, old);
64
	free(old);
65
	set_index_entry(istate, nr, ce);
66
	ce->ce_flags |= CE_UPDATE_IN_BASE;
67
	istate->cache_changed |= CE_ENTRY_CHANGED;
68 69
}

70 71 72 73 74 75 76
void rename_index_entry_at(struct index_state *istate, int nr, const char *new_name)
{
	struct cache_entry *old = istate->cache[nr], *new;
	int namelen = strlen(new_name);

	new = xmalloc(cache_entry_size(namelen));
	copy_cache_entry(new, old);
77
	new->ce_flags &= ~CE_HASHED;
78
	new->ce_namelen = namelen;
Duy Nguyen's avatar
Duy Nguyen committed
79
	new->index = 0;
80 81
	memcpy(new->name, new_name, namelen + 1);

82
	cache_tree_invalidate_path(istate, old->name);
83
	untracked_cache_remove_from_index(istate, old->name);
84 85 86 87
	remove_index_entry_at(istate, nr);
	add_index_entry(istate, new, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE);
}

88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142
void fill_stat_data(struct stat_data *sd, struct stat *st)
{
	sd->sd_ctime.sec = (unsigned int)st->st_ctime;
	sd->sd_mtime.sec = (unsigned int)st->st_mtime;
	sd->sd_ctime.nsec = ST_CTIME_NSEC(*st);
	sd->sd_mtime.nsec = ST_MTIME_NSEC(*st);
	sd->sd_dev = st->st_dev;
	sd->sd_ino = st->st_ino;
	sd->sd_uid = st->st_uid;
	sd->sd_gid = st->st_gid;
	sd->sd_size = st->st_size;
}

int match_stat_data(const struct stat_data *sd, struct stat *st)
{
	int changed = 0;

	if (sd->sd_mtime.sec != (unsigned int)st->st_mtime)
		changed |= MTIME_CHANGED;
	if (trust_ctime && check_stat &&
	    sd->sd_ctime.sec != (unsigned int)st->st_ctime)
		changed |= CTIME_CHANGED;

#ifdef USE_NSEC
	if (check_stat && sd->sd_mtime.nsec != ST_MTIME_NSEC(*st))
		changed |= MTIME_CHANGED;
	if (trust_ctime && check_stat &&
	    sd->sd_ctime.nsec != ST_CTIME_NSEC(*st))
		changed |= CTIME_CHANGED;
#endif

	if (check_stat) {
		if (sd->sd_uid != (unsigned int) st->st_uid ||
			sd->sd_gid != (unsigned int) st->st_gid)
			changed |= OWNER_CHANGED;
		if (sd->sd_ino != (unsigned int) st->st_ino)
			changed |= INODE_CHANGED;
	}

#ifdef USE_STDEV
	/*
	 * st_dev breaks on network filesystems where different
	 * clients will have different views of what "device"
	 * the filesystem is on
	 */
	if (check_stat && sd->sd_dev != (unsigned int) st->st_dev)
			changed |= INODE_CHANGED;
#endif

	if (sd->sd_size != (unsigned int) st->st_size)
		changed |= DATA_CHANGED;

	return changed;
}

143 144 145 146 147 148 149
/*
 * This only updates the "non-critical" parts of the directory
 * cache, ie the parts that aren't tracked by GIT, and only used
 * to validate the cache.
 */
void fill_stat_cache_info(struct cache_entry *ce, struct stat *st)
{
150
	fill_stat_data(&ce->ce_stat_data, st);
Junio C Hamano's avatar
Junio C Hamano committed
151 152

	if (assume_unchanged)
153
		ce->ce_flags |= CE_VALID;
154 155 156

	if (S_ISREG(st->st_mode))
		ce_mark_uptodate(ce);
157 158
}

159
static int ce_compare_data(const struct cache_entry *ce, struct stat *st)
Junio C Hamano's avatar
Junio C Hamano committed
160 161 162 163 164 165
{
	int match = -1;
	int fd = open(ce->name, O_RDONLY);

	if (fd >= 0) {
		unsigned char sha1[20];
166
		if (!index_fd(sha1, fd, st, OBJ_BLOB, ce->name, 0))
167
			match = hashcmp(sha1, ce->sha1);
168
		/* index_fd() closed the file descriptor already */
Junio C Hamano's avatar
Junio C Hamano committed
169 170 171 172
	}
	return match;
}

173
static int ce_compare_link(const struct cache_entry *ce, size_t expected_size)
Junio C Hamano's avatar
Junio C Hamano committed
174 175 176 177
{
	int match = -1;
	void *buffer;
	unsigned long size;
178
	enum object_type type;
179
	struct strbuf sb = STRBUF_INIT;
Junio C Hamano's avatar
Junio C Hamano committed
180

181
	if (strbuf_readlink(&sb, ce->name, expected_size))
Junio C Hamano's avatar
Junio C Hamano committed
182
		return -1;
183

184
	buffer = read_sha1_file(ce->sha1, &type, &size);
185 186 187 188
	if (buffer) {
		if (size == sb.len)
			match = memcmp(buffer, sb.buf, size);
		free(buffer);
Junio C Hamano's avatar
Junio C Hamano committed
189
	}
190
	strbuf_release(&sb);
Junio C Hamano's avatar
Junio C Hamano committed
191 192 193
	return match;
}

194
static int ce_compare_gitlink(const struct cache_entry *ce)
195 196 197 198 199
{
	unsigned char sha1[20];

	/*
	 * We don't actually require that the .git directory
Martin Waitz's avatar
Martin Waitz committed
200
	 * under GITLINK directory be a valid git directory. It
201 202 203 204 205 206 207 208 209 210
	 * might even be missing (in case nobody populated that
	 * sub-project).
	 *
	 * If so, we consider it always to match.
	 */
	if (resolve_gitlink_ref(ce->name, "HEAD", sha1) < 0)
		return 0;
	return hashcmp(sha1, ce->sha1);
}

211
static int ce_modified_check_fs(const struct cache_entry *ce, struct stat *st)
Junio C Hamano's avatar
Junio C Hamano committed
212 213 214 215 216 217 218
{
	switch (st->st_mode & S_IFMT) {
	case S_IFREG:
		if (ce_compare_data(ce, st))
			return DATA_CHANGED;
		break;
	case S_IFLNK:
219
		if (ce_compare_link(ce, xsize_t(st->st_size)))
Junio C Hamano's avatar
Junio C Hamano committed
220 221
			return DATA_CHANGED;
		break;
222
	case S_IFDIR:
223
		if (S_ISGITLINK(ce->ce_mode))
224
			return ce_compare_gitlink(ce) ? DATA_CHANGED : 0;
Junio C Hamano's avatar
Junio C Hamano committed
225 226 227 228 229 230
	default:
		return TYPE_CHANGED;
	}
	return 0;
}

231
static int ce_match_stat_basic(const struct cache_entry *ce, struct stat *st)
232 233 234
{
	unsigned int changed = 0;

235 236 237 238
	if (ce->ce_flags & CE_REMOVE)
		return MODE_CHANGED | DATA_CHANGED | TYPE_CHANGED;

	switch (ce->ce_mode & S_IFMT) {
239 240
	case S_IFREG:
		changed |= !S_ISREG(st->st_mode) ? TYPE_CHANGED : 0;
Junio C Hamano's avatar
Junio C Hamano committed
241 242 243 244
		/* We consider only the owner x bit to be relevant for
		 * "mode changes"
		 */
		if (trust_executable_bit &&
245
		    (0100 & (ce->ce_mode ^ st->st_mode)))
246
			changed |= MODE_CHANGED;
247 248
		break;
	case S_IFLNK:
249 250 251
		if (!S_ISLNK(st->st_mode) &&
		    (has_symlinks || !S_ISREG(st->st_mode)))
			changed |= TYPE_CHANGED;
252
		break;
Martin Waitz's avatar
Martin Waitz committed
253
	case S_IFGITLINK:
254
		/* We ignore most of the st_xxx fields for gitlinks */
255 256 257 258
		if (!S_ISDIR(st->st_mode))
			changed |= TYPE_CHANGED;
		else if (ce_compare_gitlink(ce))
			changed |= DATA_CHANGED;
259
		return changed;
260
	default:
261
		die("internal error: ce_mode is %o", ce->ce_mode);
262
	}
263

264
	changed |= match_stat_data(&ce->ce_stat_data, st);
265

266
	/* Racily smudged entry? */
267
	if (!ce->ce_stat_data.sd_size) {
268 269 270 271
		if (!is_empty_blob_sha1(ce->sha1))
			changed |= DATA_CHANGED;
	}

Junio C Hamano's avatar
Junio C Hamano committed
272 273 274
	return changed;
}

275 276
static int is_racy_stat(const struct index_state *istate,
			const struct stat_data *sd)
277
{
278
	return (istate->timestamp.sec &&
279 280
#ifdef USE_NSEC
		 /* nanosecond timestamped files can also be racy! */
281 282 283
		(istate->timestamp.sec < sd->sd_mtime.sec ||
		 (istate->timestamp.sec == sd->sd_mtime.sec &&
		  istate->timestamp.nsec <= sd->sd_mtime.nsec))
284
#else
285
		istate->timestamp.sec <= sd->sd_mtime.sec
286
#endif
287 288 289 290 291 292 293 294
		);
}

static int is_racy_timestamp(const struct index_state *istate,
			     const struct cache_entry *ce)
{
	return (!S_ISGITLINK(ce->ce_mode) &&
		is_racy_stat(istate, &ce->ce_stat_data));
295 296
}

297 298 299 300 301 302
int match_stat_data_racy(const struct index_state *istate,
			 const struct stat_data *sd, struct stat *st)
{
	if (is_racy_stat(istate, sd))
		return MTIME_CHANGED;
	return match_stat_data(sd, st);
303 304
}

305
int ie_match_stat(const struct index_state *istate,
306
		  const struct cache_entry *ce, struct stat *st,
307
		  unsigned int options)
Junio C Hamano's avatar
Junio C Hamano committed
308
{
Junio C Hamano's avatar
Junio C Hamano committed
309
	unsigned int changed;
310
	int ignore_valid = options & CE_MATCH_IGNORE_VALID;
311
	int ignore_skip_worktree = options & CE_MATCH_IGNORE_SKIP_WORKTREE;
312
	int assume_racy_is_modified = options & CE_MATCH_RACY_IS_DIRTY;
Junio C Hamano's avatar
Junio C Hamano committed
313 314 315 316

	/*
	 * If it's marked as always valid in the index, it's
	 * valid whatever the checked-out copy says.
317 318
	 *
	 * skip-worktree has the same effect with higher precedence
Junio C Hamano's avatar
Junio C Hamano committed
319
	 */
320 321
	if (!ignore_skip_worktree && ce_skip_worktree(ce))
		return 0;
322
	if (!ignore_valid && (ce->ce_flags & CE_VALID))
Junio C Hamano's avatar
Junio C Hamano committed
323 324
		return 0;

325 326 327 328 329
	/*
	 * Intent-to-add entries have not been added, so the index entry
	 * by definition never matches what is in the work tree until it
	 * actually gets added.
	 */
330
	if (ce_intent_to_add(ce))
331 332
		return DATA_CHANGED | TYPE_CHANGED | MODE_CHANGED;

Junio C Hamano's avatar
Junio C Hamano committed
333
	changed = ce_match_stat_basic(ce, st);
Junio C Hamano's avatar
Junio C Hamano committed
334

Junio C Hamano's avatar
Junio C Hamano committed
335 336 337 338 339 340 341 342 343 344 345 346 347 348
	/*
	 * Within 1 second of this sequence:
	 * 	echo xyzzy >file && git-update-index --add file
	 * running this command:
	 * 	echo frotz >file
	 * would give a falsely clean cache entry.  The mtime and
	 * length match the cache, and other stat fields do not change.
	 *
	 * We could detect this at update-index time (the cache entry
	 * being registered/updated records the same time as "now")
	 * and delay the return from git-update-index, but that would
	 * effectively mean we can make at most one commit per second,
	 * which is not acceptable.  Instead, we check cache entries
	 * whose mtime are the same as the index file timestamp more
Junio C Hamano's avatar
Junio C Hamano committed
349
	 * carefully than others.
Junio C Hamano's avatar
Junio C Hamano committed
350
	 */
351
	if (!changed && is_racy_timestamp(istate, ce)) {
352 353 354 355 356
		if (assume_racy_is_modified)
			changed |= DATA_CHANGED;
		else
			changed |= ce_modified_check_fs(ce, st);
	}
357

Junio C Hamano's avatar
Junio C Hamano committed
358
	return changed;
359 360
}

361
int ie_modified(const struct index_state *istate,
362 363
		const struct cache_entry *ce,
		struct stat *st, unsigned int options)
364
{
Junio C Hamano's avatar
Junio C Hamano committed
365
	int changed, changed_fs;
366 367

	changed = ie_match_stat(istate, ce, st, options);
368 369 370 371 372 373 374 375 376
	if (!changed)
		return 0;
	/*
	 * If the mode or type has changed, there's no point in trying
	 * to refresh the entry - it's not going to match
	 */
	if (changed & (MODE_CHANGED | TYPE_CHANGED))
		return changed;

377 378 379 380 381 382 383 384 385 386 387 388 389
	/*
	 * Immediately after read-tree or update-index --cacheinfo,
	 * the length field is zero, as we have never even read the
	 * lstat(2) information once, and we cannot trust DATA_CHANGED
	 * returned by ie_match_stat() which in turn was returned by
	 * ce_match_stat_basic() to signal that the filesize of the
	 * blob changed.  We have to actually go to the filesystem to
	 * see if the contents match, and if so, should answer "unchanged".
	 *
	 * The logic does not apply to gitlinks, as ce_match_stat_basic()
	 * already has checked the actual HEAD from the filesystem in the
	 * subproject.  If ie_match_stat() already said it is different,
	 * then we know it is.
390
	 */
391
	if ((changed & DATA_CHANGED) &&
392
	    (S_ISGITLINK(ce->ce_mode) || ce->ce_stat_data.sd_size != 0))
393 394
		return changed;

Junio C Hamano's avatar
Junio C Hamano committed
395 396 397
	changed_fs = ce_modified_check_fs(ce, st);
	if (changed_fs)
		return changed | changed_fs;
398 399 400
	return 0;
}

401 402 403 404 405 406 407 408 409 410 411 412
int base_name_compare(const char *name1, int len1, int mode1,
		      const char *name2, int len2, int mode2)
{
	unsigned char c1, c2;
	int len = len1 < len2 ? len1 : len2;
	int cmp;

	cmp = memcmp(name1, name2, len);
	if (cmp)
		return cmp;
	c1 = name1[len];
	c2 = name2[len];
413
	if (!c1 && S_ISDIR(mode1))
414
		c1 = '/';
415
	if (!c2 && S_ISDIR(mode2))
416 417 418 419
		c2 = '/';
	return (c1 < c2) ? -1 : (c1 > c2) ? 1 : 0;
}

420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454
/*
 * df_name_compare() is identical to base_name_compare(), except it
 * compares conflicting directory/file entries as equal. Note that
 * while a directory name compares as equal to a regular file, they
 * then individually compare _differently_ to a filename that has
 * a dot after the basename (because '\0' < '.' < '/').
 *
 * This is used by routines that want to traverse the git namespace
 * but then handle conflicting entries together when possible.
 */
int df_name_compare(const char *name1, int len1, int mode1,
		    const char *name2, int len2, int mode2)
{
	int len = len1 < len2 ? len1 : len2, cmp;
	unsigned char c1, c2;

	cmp = memcmp(name1, name2, len);
	if (cmp)
		return cmp;
	/* Directories and files compare equal (same length, same name) */
	if (len1 == len2)
		return 0;
	c1 = name1[len];
	if (!c1 && S_ISDIR(mode1))
		c1 = '/';
	c2 = name2[len];
	if (!c2 && S_ISDIR(mode2))
		c2 = '/';
	if (c1 == '/' && !c2)
		return 0;
	if (c2 == '/' && !c1)
		return 0;
	return c1 - c2;
}

455
int name_compare(const char *name1, size_t len1, const char *name2, size_t len2)
456
{
457 458
	size_t min_len = (len1 < len2) ? len1 : len2;
	int cmp = memcmp(name1, name2, min_len);
459 460 461 462 463 464
	if (cmp)
		return cmp;
	if (len1 < len2)
		return -1;
	if (len1 > len2)
		return 1;
465 466 467 468 469 470 471 472 473 474
	return 0;
}

int cache_name_stage_compare(const char *name1, int len1, int stage1, const char *name2, int len2, int stage2)
{
	int cmp;

	cmp = name_compare(name1, len1, name2, len2);
	if (cmp)
		return cmp;
Junio C Hamano's avatar
Junio C Hamano committed
475

476
	if (stage1 < stage2)
477
		return -1;
478
	if (stage1 > stage2)
479
		return 1;
480 481 482
	return 0;
}

483
static int index_name_stage_pos(const struct index_state *istate, const char *name, int namelen, int stage)
484 485 486 487
{
	int first, last;

	first = 0;
488
	last = istate->cache_nr;
489 490
	while (last > first) {
		int next = (last + first) >> 1;
491
		struct cache_entry *ce = istate->cache[next];
492
		int cmp = cache_name_stage_compare(name, namelen, stage, ce->name, ce_namelen(ce), ce_stage(ce));
493
		if (!cmp)
494
			return next;
495 496 497 498 499 500
		if (cmp < 0) {
			last = next;
			continue;
		}
		first = next+1;
	}
501
	return -first-1;
502 503
}

504 505 506 507 508
int index_name_pos(const struct index_state *istate, const char *name, int namelen)
{
	return index_name_stage_pos(istate, name, namelen, 0);
}

509
/* Remove entry, return true if there are more entries to go.. */
510
int remove_index_entry_at(struct index_state *istate, int pos)
511
{
512 513
	struct cache_entry *ce = istate->cache[pos];

514
	record_resolve_undo(istate, ce);
515
	remove_name_hash(istate, ce);
516
	save_or_free_index_entry(istate, ce);
517
	istate->cache_changed |= CE_ENTRY_REMOVED;
518 519
	istate->cache_nr--;
	if (pos >= istate->cache_nr)
520
		return 0;
521 522 523
	memmove(istate->cache + pos,
		istate->cache + pos + 1,
		(istate->cache_nr - pos) * sizeof(struct cache_entry *));
524 525 526
	return 1;
}

527
/*
Ondřej Bílka's avatar
Ondřej Bílka committed
528
 * Remove all cache entries marked for removal, that is where
529 530 531 532 533 534 535 536 537
 * CE_REMOVE is set in ce_flags.  This is much more effective than
 * calling remove_index_entry_at() for each entry to be removed.
 */
void remove_marked_cache_entries(struct index_state *istate)
{
	struct cache_entry **ce_array = istate->cache;
	unsigned int i, j;

	for (i = j = 0; i < istate->cache_nr; i++) {
538
		if (ce_array[i]->ce_flags & CE_REMOVE) {
539
			remove_name_hash(istate, ce_array[i]);
540
			save_or_free_index_entry(istate, ce_array[i]);
541
		}
542 543 544
		else
			ce_array[j++] = ce_array[i];
	}
545 546
	if (j == istate->cache_nr)
		return;
547
	istate->cache_changed |= CE_ENTRY_REMOVED;
548 549 550
	istate->cache_nr = j;
}

551
int remove_file_from_index(struct index_state *istate, const char *path)
552
{
553
	int pos = index_name_pos(istate, path, strlen(path));
554 555
	if (pos < 0)
		pos = -pos-1;
556
	cache_tree_invalidate_path(istate, path);
557
	untracked_cache_remove_from_index(istate, path);
558 559
	while (pos < istate->cache_nr && !strcmp(istate->cache[pos]->name, path))
		remove_index_entry_at(istate, pos);
560 561 562
	return 0;
}

563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590
static int compare_name(struct cache_entry *ce, const char *path, int namelen)
{
	return namelen != ce_namelen(ce) || memcmp(path, ce->name, namelen);
}

static int index_name_pos_also_unmerged(struct index_state *istate,
	const char *path, int namelen)
{
	int pos = index_name_pos(istate, path, namelen);
	struct cache_entry *ce;

	if (pos >= 0)
		return pos;

	/* maybe unmerged? */
	pos = -1 - pos;
	if (pos >= istate->cache_nr ||
			compare_name((ce = istate->cache[pos]), path, namelen))
		return -1;

	/* order of preference: stage 2, 1, 3 */
	if (ce_stage(ce) == 1 && pos + 1 < istate->cache_nr &&
			ce_stage((ce = istate->cache[pos + 1])) == 2 &&
			!compare_name(ce, path, namelen))
		pos++;
	return pos;
}

591 592 593 594 595 596 597 598 599 600 601 602 603 604 605
static int different_name(struct cache_entry *ce, struct cache_entry *alias)
{
	int len = ce_namelen(ce);
	return ce_namelen(alias) != len || memcmp(ce->name, alias->name, len);
}

/*
 * If we add a filename that aliases in the cache, we will use the
 * name that we already have - but we don't want to update the same
 * alias twice, because that implies that there were actually two
 * different files with aliasing names!
 *
 * So we use the CE_ADDED flag to verify that the alias was an old
 * one before we accept it as
 */
606 607 608
static struct cache_entry *create_alias_ce(struct index_state *istate,
					   struct cache_entry *ce,
					   struct cache_entry *alias)
609 610 611 612 613 614 615 616 617 618 619 620
{
	int len;
	struct cache_entry *new;

	if (alias->ce_flags & CE_ADDED)
		die("Will not add file alias '%s' ('%s' already exists in index)", ce->name, alias->name);

	/* Ok, create the new entry using the name of the existing alias */
	len = ce_namelen(alias);
	new = xcalloc(1, cache_entry_size(len));
	memcpy(new->name, alias->name, len);
	copy_cache_entry(new, ce);
621
	save_or_free_index_entry(istate, ce);
622 623 624
	return new;
}

625
void set_object_name_for_intent_to_add_entry(struct cache_entry *ce)
626 627 628 629 630 631 632
{
	unsigned char sha1[20];
	if (write_sha1_file("", 0, blob_type, sha1))
		die("cannot create an empty blob in the object database");
	hashcpy(ce->sha1, sha1);
}

633
int add_to_index(struct index_state *istate, const char *path, struct stat *st, int flags)
Johannes Schindelin's avatar
Johannes Schindelin committed
634
{
635
	int size, namelen, was_same;
636
	mode_t st_mode = st->st_mode;
637
	struct cache_entry *ce, *alias;
638
	unsigned ce_option = CE_MATCH_IGNORE_VALID|CE_MATCH_IGNORE_SKIP_WORKTREE|CE_MATCH_RACY_IS_DIRTY;
639 640
	int verbose = flags & (ADD_CACHE_VERBOSE | ADD_CACHE_PRETEND);
	int pretend = flags & ADD_CACHE_PRETEND;
641 642 643
	int intent_only = flags & ADD_CACHE_INTENT;
	int add_option = (ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE|
			  (intent_only ? ADD_CACHE_NEW_ONLY : 0));
Johannes Schindelin's avatar
Johannes Schindelin committed
644

645
	if (!S_ISREG(st_mode) && !S_ISLNK(st_mode) && !S_ISDIR(st_mode))
646
		return error("%s: can only add regular files, symbolic links or git-directories", path);
Johannes Schindelin's avatar
Johannes Schindelin committed
647 648

	namelen = strlen(path);
649
	if (S_ISDIR(st_mode)) {
650 651 652
		while (namelen && path[namelen-1] == '/')
			namelen--;
	}
Johannes Schindelin's avatar
Johannes Schindelin committed
653 654 655
	size = cache_entry_size(namelen);
	ce = xcalloc(1, size);
	memcpy(ce->name, path, namelen);
656
	ce->ce_namelen = namelen;
657 658
	if (!intent_only)
		fill_stat_cache_info(ce, st);
659 660
	else
		ce->ce_flags |= CE_INTENT_TO_ADD;
Johannes Schindelin's avatar
Johannes Schindelin committed
661

662
	if (trust_executable_bit && has_symlinks)
663
		ce->ce_mode = create_ce_mode(st_mode);
664
	else {
665 666
		/* If there is an existing entry, pick the mode bits and type
		 * from it, otherwise assume unexecutable regular file.
Johannes Schindelin's avatar
Johannes Schindelin committed
667
		 */
668
		struct cache_entry *ent;
669
		int pos = index_name_pos_also_unmerged(istate, path, namelen);
670

671
		ent = (0 <= pos) ? istate->cache[pos] : NULL;
672
		ce->ce_mode = ce_mode_from_stat(ent, st_mode);
Johannes Schindelin's avatar
Johannes Schindelin committed
673 674
	}

675 676 677 678 679 680
	/* When core.ignorecase=true, determine if a directory of the same name but differing
	 * case already exists within the Git repository.  If it does, ensure the directory
	 * case of the file being added to the repository matches (is folded into) the existing
	 * entry's directory case.
	 */
	if (ignore_case) {
681
		adjust_dirname_case(istate, ce->name);
682 683
	}

684
	alias = index_file_exists(istate, ce->name, ce_namelen(ce), ignore_case);
685
	if (alias && !ce_stage(alias) && !ie_match_stat(istate, alias, st, ce_option)) {
686
		/* Nothing changed, really */
687 688
		if (!S_ISGITLINK(alias->ce_mode))
			ce_mark_uptodate(alias);
689
		alias->ce_flags |= CE_ADDED;
690 691

		free(ce);
692 693
		return 0;
	}
694
	if (!intent_only) {
695 696
		if (index_path(ce->sha1, path, st, HASH_WRITE_OBJECT)) {
			free(ce);
697
			return error("unable to index file %s", path);
698
		}
699
	} else
700
		set_object_name_for_intent_to_add_entry(ce);
701

702
	if (ignore_case && alias && different_name(ce, alias))
703
		ce = create_alias_ce(istate, ce, alias);
704
	ce->ce_flags |= CE_ADDED;
705

Junio C Hamano's avatar
Junio C Hamano committed
706
	/* It was suspected to be racily clean, but it turns out to be Ok */
707 708 709 710 711 712
	was_same = (alias &&
		    !ce_stage(alias) &&
		    !hashcmp(alias->sha1, ce->sha1) &&
		    ce->ce_mode == alias->ce_mode);

	if (pretend)
713 714 715 716 717
		free(ce);
	else if (add_index_entry(istate, ce, add_option)) {
		free(ce);
		return error("unable to add %s to index", path);
	}
718
	if (verbose && !was_same)
Johannes Schindelin's avatar
Johannes Schindelin committed
719 720 721 722
		printf("add '%s'\n", path);
	return 0;
}

723
int add_file_to_index(struct index_state *istate, const char *path, int flags)
724 725 726
{
	struct stat st;
	if (lstat(path, &st))
727
		die_errno("unable to stat '%s'", path);
728
	return add_to_index(istate, path, &st, flags);
729 730
}

731 732
struct cache_entry *make_cache_entry(unsigned int mode,
		const unsigned char *sha1, const char *path, int stage,
733
		unsigned int refresh_options)
734 735
{
	int size, len;
736
	struct cache_entry *ce, *ret;
737

738 739
	if (!verify_path(path)) {
		error("Invalid path '%s'", path);
740
		return NULL;
741
	}
742 743 744 745 746 747 748

	len = strlen(path);
	size = cache_entry_size(len);
	ce = xcalloc(1, size);

	hashcpy(ce->sha1, sha1);
	memcpy(ce->name, path, len);
749 750
	ce->ce_flags = create_ce_flags(stage);
	ce->ce_namelen = len;
751 752
	ce->ce_mode = create_ce_mode(mode);

753
	ret = refresh_cache_entry(ce, refresh_options);
Stefan Beller's avatar
Stefan Beller committed
754
	if (ret != ce)
755
		free(ce);
Stefan Beller's avatar
Stefan Beller committed
756
	return ret;
757 758
}

759
int ce_same_name(const struct cache_entry *a, const struct cache_entry *b)
760 761 762 763 764
{
	int len = ce_namelen(a);
	return ce_namelen(b) == len && !memcmp(a->name, b->name, len);
}

765 766 767 768 769 770 771 772 773 774 775 776 777 778 779
/*
 * We fundamentally don't like some paths: we don't want
 * dot or dot-dot anywhere, and for obvious reasons don't
 * want to recurse into ".git" either.
 *
 * Also, we don't want double slashes or slashes at the
 * end that can make pathnames ambiguous.
 */
static int verify_dotfile(const char *rest)
{
	/*
	 * The first character was '.', but that
	 * has already been discarded, we now test
	 * the rest.
	 */
780

781
	/* "." is not allowed */
782
	if (*rest == '\0' || is_dir_sep(*rest))
783 784
		return 0;

785
	switch (*rest) {
786 787 788 789 790
	/*
	 * ".git" followed by  NUL or slash is bad. This
	 * shares the path end test with the ".." case.
	 */
	case 'g':
791 792
	case 'G':
		if (rest[1] != 'i' && rest[1] != 'I')
793
			break;
794
		if (rest[2] != 't' && rest[2] != 'T')
795 796 797 798
			break;
		rest += 2;
	/* fallthrough */
	case '.':
799
		if (rest[1] == '\0' || is_dir_sep(rest[1]))
800 801 802 803 804 805 806 807 808
			return 0;
	}
	return 1;
}

int verify_path(const char *path)
{
	char c;

809 810 811
	if (has_dos_drive_prefix(path))
		return 0;

812 813 814 815
	goto inside;
	for (;;) {
		if (!c)
			return 1;
816
		if (is_dir_sep(c)) {
817
inside:
818 819
			if (protect_hfs && is_hfs_dotgit(path))
				return 0;
820 821
			if (protect_ntfs && is_ntfs_dotgit(path))
				return 0;
822
			c = *path++;
823 824 825
			if ((c == '.' && !verify_dotfile(path)) ||
			    is_dir_sep(c) || c == '\0')
				return 0;
826 827 828 829 830
		}
		c = *path++;
	}
}

831 832 833
/*
 * Do we have another file that has the beginning components being a
 * proper superset of the name we're trying to add?
834
 */
835 836
static int has_file_name(struct index_state *istate,
			 const struct cache_entry *ce, int pos, int ok_to_replace)
837
{
838 839
	int retval = 0;
	int len = ce_namelen(ce);
840
	int stage = ce_stage(ce);
841
	const char *name = ce->name;
842

843 844
	while (pos < istate->cache_nr) {
		struct cache_entry *p = istate->cache[pos++];
845

846
		if (len >= ce_namelen(p))
847
			break;
848 849
		if (memcmp(name, p->name, len))
			break;
850 851
		if (ce_stage(p) != stage)
			continue;
852 853
		if (p->name[len] != '/')
			continue;
854
		if (p->ce_flags & CE_REMOVE)
855
			continue;
856 857 858
		retval = -1;
		if (!ok_to_replace)
			break;
859
		remove_index_entry_at(istate, --pos);
860
	}
861 862
	return retval;
}
863

864 865 866 867
/*
 * Do we have another file with a pathname that is a proper
 * subset of the name we're trying to add?
 */
868 869
static int has_dir_name(struct index_state *istate,
			const struct cache_entry *ce, int pos, int ok_to_replace)
870 871
{
	int retval = 0;
872
	int stage = ce_stage(ce);
873 874
	const char *name = ce->name;
	const char *slash = name + ce_namelen(ce);
875

876 877
	for (;;) {
		int len;
878

879 880 881 882 883 884 885
		for (;;) {
			if (*--slash == '/')
				break;
			if (slash <= ce->name)
				return retval;
		}
		len = slash - name;
886

887
		pos = index_name_stage_pos(istate, name, len, stage);
888
		if (pos >= 0) {
889 890 891 892 893 894 895 896
			/*
			 * Found one, but not so fast.  This could
			 * be a marker that says "I was here, but
			 * I am being removed".  Such an entry is
			 * not a part of the resulting tree, and
			 * it is Ok to have a directory at the same
			 * path.
			 */
897
			if (!(istate->cache[pos]->ce_flags & CE_REMOVE)) {
898 899 900
				retval = -1;
				if (!ok_to_replace)
					break;
901
				remove_index_entry_at(istate, pos);
902 903
				continue;
			}
904
		}
905 906
		else
			pos = -pos-1;
907 908 909 910

		/*
		 * Trivial optimization: if we find an entry that
		 * already matches the sub-directory, then we know
911
		 * we're ok, and we can exit.
912
		 */
913 914
		while (pos < istate->cache_nr) {
			struct cache_entry *p = istate->cache[pos];
915 916 917 918
			if ((ce_namelen(p) <= len) ||
			    (p->name[len] != '/') ||
			    memcmp(p->name, name, len))
				break; /* not our subdirectory */
919 920 921
			if (ce_stage(p) == stage && !(p->ce_flags & CE_REMOVE))
				/*
				 * p is at the same stage as our entry, and
922 923 924 925 926 927
				 * is a subdirectory of what we are looking
				 * at, so we cannot have conflicts at our
				 * level or anything shorter.
				 */
				return retval;
			pos++;
928
		}
929
	}
930 931 932 933 934 935 936
	return retval;
}

/* We may be in a situation where we already have path/file and path
 * is being added, or we already have path and path/file is being
 * added.  Either one would result in a nonsense tree that has path
 * twice when git-write-tree tries to write it out.  Prevent it.
Junio C Hamano's avatar
Junio C Hamano committed
937
 *
938 939 940 941
 * If ok-to-replace is specified, we remove the conflicting entries
 * from the cache so the caller should recompute the insert position.
 * When this happens, we return non-zero.
 */
942 943 944
static int check_file_directory_conflict(struct index_state *istate,
					 const struct cache_entry *ce,
					 int pos, int ok_to_replace)
945
{
946 947 948 949 950
	int retval;

	/*
	 * When ce is an "I am going away" entry, we allow it to be added
	 */
951
	if (ce->ce_flags & CE_REMOVE)
952 953
		return 0;

954 955 956
	/*
	 * We check if the path is a sub-path of a subsequent pathname
	 * first, since removing those will not change the position
957
	 * in the array.
958
	 */
959
	retval = has_file_name(istate, ce, pos, ok_to_replace);
960

961 962 963 964
	/*
	 * Then check if the path might have a clashing sub-directory
	 * before it.
	 */
965
	return retval + has_dir_name(istate, ce, pos, ok_to_replace);
966 967
}

968
static int add_index_entry_with_check(struct index_state *istate, struct cache_entry *ce, int option)
969 970
{
	int pos;
971 972
	int ok_to_add = option & ADD_CACHE_OK_TO_ADD;
	int ok_to_replace = option & ADD_CACHE_OK_TO_REPLACE;
973
	int skip_df_check = option & ADD_CACHE_SKIP_DFCHECK;
974
	int new_only = option & ADD_CACHE_NEW_ONLY;
Junio C Hamano's avatar
Junio C Hamano committed
975

976 977
	if (!(option & ADD_CACHE_KEEP_CACHE_TREE))
		cache_tree_invalidate_path(istate, ce->name);
978
	pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce));
979

Junio C Hamano's avatar
Junio C Hamano committed
980
	/* existing match? Just replace it. */
981
	if (pos >= 0) {
982 983
		if (!new_only)
			replace_index_entry(istate, pos, ce);
984 985
		return 0;
	}
986
	pos = -pos-1;
987

988 989
	if (!(option & ADD_CACHE_KEEP_CACHE_TREE))
		untracked_cache_add_to_index(istate, ce->name);
990

991 992 993 994
	/*
	 * Inserting a merged entry ("stage 0") into the index
	 * will always replace all non-merged entries..
	 */
995 996
	if (pos < istate->cache_nr && ce_stage(ce) == 0) {
		while (ce_same_name(istate->cache[pos], ce)) {
997
			ok_to_add = 1;
998
			if (!remove_index_entry_at(istate, pos))
999 1000 1001 1002
				break;
		}
	}

1003 1004
	if (!ok_to_add)
		return -1;
1005
	if (!verify_path(ce->name))
1006
		return error("Invalid path '%s'", ce->name);
1007

Junio C Hamano's avatar
Junio C Hamano committed
1008
	if (!skip_df_check &&
1009
	    check_file_directory_conflict(istate, ce, pos, ok_to_replace)) {
1010
		if (!ok_to_replace)
1011 1012
			return error("'%s' appears as both a file and as a directory",
				     ce->name);
1013
		pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce));
1014 1015
		pos = -pos-1;
	}
1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031
	return pos + 1;
}

int add_index_entry(struct index_state *istate, struct cache_entry *ce, int option)
{
	int pos;

	if (option & ADD_CACHE_JUST_APPEND)
		pos = istate->cache_nr;
	else {
		int ret;
		ret = add_index_entry_with_check(istate, ce, option);
		if (ret <= 0)
			return ret;
		pos = ret - 1;
	}
1032

1033
	/* Make sure the array is big enough .. */
1034
	ALLOC_GROW(istate->cache, istate->cache_nr + 1, istate->cache_alloc);
1035 1036

	/* Add it in.. */
1037
	istate->cache_nr++;
1038
	if (istate->cache_nr > pos + 1)